Web HIV Treatment Expert

posted: 08/10/2010

A free ground-breaking web tool is now available to help doctors and people with HIV choose the best HIV treatment for each person. RDI, a UK-based not-for-profit research group, have launched a system for predicting how each individual would respond to different drugs. The experimental system is called the HIV Treatment Response Prediction System (HIV-TRePS).

Uses all the evidence
HIV-TRePS uses complex computer models which are trained to be experts by using all the data from the experience of treating of tens of thousands of people with HIV. HIV doctors log in to the site, then enter data like CD4 and viral load, the HIV sub-type and its mutations, previous HIV treatment history and any HIV treatment preferences. Within seconds, the software produces a report of the next treatment combinations that have the best chances of success, based on all the evidence. It is designed to help with the complicated problem of working out what to use next, when treatment change becomes needed; it is not for choosing the first HIV treatment combination, which is much simpler.

This easy-to-use system has proven to be a significantly more accurate predictor of response than the current system of genotyping with rules-based interpretation to help drug selection.

Better treatment around the world
Studies conducted by the RDI and its partners have demonstrated that the system can potentially improve the health and lifespan of people with HIV and reduce the number of drugs used and therefore the total cost of treatment.

"This is a very exciting development: the system literally puts the experience of treating thousands of different patients at the doctor's fingertips," commented Dr. Julio Montaner, Past President of the International AIDS Society and Director of the BC Centre for Excellence in HIV & AIDS, based in Vancouver, Canada. "This has the potential to improve outcomes for people living with HIV and AIDS around the world, particularly where resources and expertise are scarce."

Takes the headaches out of HIV prescribing
Selecting and changing treatments for people with HIV in order to keep the virus suppressed is complex and challenging. There are approximately 25 HIV drugs available, and normally a combination of three or more are used to suppress the virus. However, the virus mutates and this can cause resistance to the drugs used against it. This requires a change of the treatment combination to keep containing the virus.

Random Forests for accuracy
The computational models used inside HIV-TRePS, are called "Random Forests," and base their predictions on a range of more than 80 different variables. These include mutations in the viral genetic code, the drugs used to treat the patient in the past, CD4 cell counts (the type of white blood cell that is attacked by HIV) and the amount of virus in the bloodstream.

The software estimates the probability of each combination of drugs reducing the amount of virus so it becomes undetectable, based on what the system has 'learnt' during its training with thousands of real clinical cases. The system's overall accuracy during development and testing was approximately 80%.

Developing world version on the way
The RDI is already working on a version of HIV-TRePS for use in resource-limited settings where there are fewer treatment options and where health care workers do not have all the information that this software requires.
 

HIV Treatment Response Prediction System (HIV-TRePS)